← Search

Chengzhi Liu

7 accepted papers

2026

Presenting a Paper is an Art: Self-Improvement Aesthetic Agents for Academic Presentations

ICLR 2026poster

The promotion of academic papers has become an important means of enhancing research visibility. where the appeal of dissemination largely determines its effectiveness. However, existing automated methods struggle limited storytelling, insufficient aesthetic quality, and constrained self-adjustment,…

Cited by 0SourcecodeScholar
2025

Incomplete Modality Disentangled Representation for Ophthalmic Disease Grading and Diagnosis

AAAI 2025technical

Ophthalmologists typically require multimodal data sources to improve diagnostic accuracy in clinical decisions. However, due to medical device shortages, low-quality data and data privacy concerns, missing data modalities are common in real-world scenarios. Existing deep learning methods tend to ad…

Cited by 1SourcePDFScholar
2025

Intervening Anchor Token: Decoding Strategy in Alleviating Hallucinations for MLLMs

ICLR 2025poster

Multimodal large language models (MLLMs) offer a powerful mechanism for interpreting visual information. However, they often suffer from hallucinations, which impede the real-world usage of these models. Existing methods attempt to alleviate this issue by designing special decoding strategies that p…

Cited by 1SourcePDFScholar
2025

MMRC: A Large-Scale Benchmark for Understanding Multimodal Large Language Model in Real-World Conversation

ACL 2025long

Recent multimodal large language models (MLLMs) have demonstrated significant potential in open-ended conversation, generating more accurate and personalized responses. However, their abilities to memorize, recall, and reason in sustained interactions within real-world scenarios remain underexplored…

2025

More Thinking, Less Seeing? Assessing Amplified Hallucination in Multimodal Reasoning Models

NeurIPS 2025poster

Test-time compute has empowered multimodal large language models to generate extended reasoning chains, yielding strong performance on tasks such as multimodal math reasoning. However, we observe that this improved reasoning ability often comes with increased hallucination: as generations become lon…

Cited by 0SourceScholar
2025

Multimodal Situational Safety

ICLR 2025poster

Multimodal Large Language Models (MLLMs) are rapidly evolving, demonstrating impressive capabilities as multimodal assistants that interact with both humans and their environments. However, this increased sophistication introduces significant safety concerns. In this paper, we present the first eval…

Cited by 5SourcePDFScholar
2025

Seeing Far and Clearly: Mitigating Hallucinations in MLLMs with Attention Causal Decoding

CVPR 2025poster

Recent advancements in multimodal large language models (MLLMs) have significantly improved performance in visual question answering. However, they often suffer from hallucinations. In this work, hallucinations are categorized into two main types: initial hallucinations and snowball hallucinations.…

Cited by 0SourcePDFScholar